Model comparison
Gemini 3.7 Flash vs Qwen3.5 397B-A17B
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 46.0 on the Noometry Index.
Last verified . 30 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 30 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 9 categories and Qwen3.5 397B-A17B in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.0 to 34.5.
- The biggest single-benchmark swing is APEX-Agents: 67.8% for Gemini 3.7 Flash and 24.9% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 262K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.7 Flash | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 59.8 | 46.0 |
| Released | 2026-08-13 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.75 | $0.60 |
| Output $ / M tokens | $3.75 | $3.60 |
| Results tracked | 44 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.7 Flash leads
Gemini 3.7 Flash: 56.2 (#22), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1592 | 1400 |
| LMArena Coding | 1497 | 1465 |
| DeepSWE | 65.5% | — |
| FrontierCode | 43.6% | — |
| FrontierSWE | 20.3% | — |
| SciCode | 59.8% | — |
| ALE-Bench | 904.3 | — |
Agentic & Tool Use Gemini 3.7 Flash leads
Gemini 3.7 Flash: 42.1 (#19), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | 67.8% | 24.9% |
| Remote Labor Index | 5% | — |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| GDP.pdf | 23.8% | — |
Reasoning Gemini 3.7 Flash leads
Gemini 3.7 Flash: 70.0 (#15), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| NYT Connections (extended) | 94% | 58.9% |
| Chess Puzzles | 47% | 13% |
| LMArena Hard Prompts | 1494 | 1448 |
| Mystery Game Puzzles | 37% | 18% |
| DTBench | 96.8% | 87.5% |
| LMCA | 50.4% | 37.9% |
| Epoch Capabilities Index | 157.27 | 146.65 |
| ARC-AGI-2 | 84.6% | — |
| Kagi LLM Benchmark | — | 73.7% |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 14.3% | — |
| Thematic Generalization | — | 65.1% |
Math Gemini 3.7 Flash leads
Gemini 3.7 Flash: 69.6 (#23), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 71.6% | 31.2% |
| OTIS Mock AIME 2024-2025 | 97.2% | 88.9% |
| LMArena Math | 1507 | 1454 |
| FrontierMath Tier 4 | 36.6% | — |
| ProofBench | 58% | — |
Knowledge Gemini 3.7 Flash leads
Gemini 3.7 Flash: 69.7 (#5), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 94.8% | 86.4% |
| LMArena Expert | 1508 | 1462 |
| SimpleQA Verified | 69.2% | — |
Multimodal Qwen3.5 397B-A17B leads
Gemini 3.7 Flash: 37.3 (#73), Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1316 | 1263 |
| Furniture Assembly | 26.7% | — |
Multilingual Gemini 3.7 Flash leads
Gemini 3.7 Flash: 57.6 (#7), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1484 | 1430 |
| LMArena Chinese | 1548 | 1500 |
| LMArena French | 1505 | 1461 |
| LMArena German | 1498 | 1447 |
| LMArena Japanese | 1512 | 1426 |
| LMArena Korean | 1483 | 1384 |
| LMArena Russian | 1516 | 1429 |
| LMArena Spanish | 1503 | 1441 |
Instruction Following Gemini 3.7 Flash leads
Gemini 3.7 Flash: 77.7 (#15), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1483 | 1424 |
Long Context Gemini 3.7 Flash leads
Gemini 3.7 Flash: 45.7 (#30), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1492 | 1442 |
Writing & Preference Gemini 3.7 Flash leads
Gemini 3.7 Flash: 71.2 (#20), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Gemini 3.7 Flash | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1486 | 1438 |
| LMArena Creative Writing | 1490 | 1401 |
| EQ-Bench Creative Writing | 1723 | 1478 |
| LMArena Multi-Turn | 1489 | 1446 |
Frequently asked questions
Is Gemini 3.7 Flash better than Qwen3.5 397B-A17B?
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 46.0 on the Noometry Index.
Which is cheaper, Gemini 3.7 Flash or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.
Is Gemini 3.7 Flash or Qwen3.5 397B-A17B better for coding?
Gemini 3.7 Flash scores higher on coding benchmarks: 56.2 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.7 Flash does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 3.7 Flash and Qwen3.5 397B-A17B share?
30 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Qwen3.5 397B-A17B has 36.